Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition

U. Bhattacharya; S.K. Parui; B. Shaw; K. Bhattacharya

inria-00104481, version 1

Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition

U. Bhattacharya () ¹, S.K. Parui () ¹, B. Shaw () ¹, K. Bhattacharya () ²

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

1: Computer Vision and Pattern Recognition Unit (CVPR)
Indian Statistical Institute India
2: Department of Computer Science & Engineering
University of Calcutta India

Bibliographic reference

Attached file list to this document:

PDF

cr1087131586696.pdf

(298.1 KB)

inria-00104481, version 1
http://hal.inria.fr/inria-00104481
oai:hal.inria.fr:inria-00104481
From: Anne Jaigu <>
Submitted on: Friday, 6 October 2006 15:56:58
Updated on: Friday, 6 October 2006 16:02:56

See short view

Associated documents

PDF :

Export

Bibtex EndNote TEI RefWorks

%% inria-00104481, version 1
%% http://hal.inria.fr/inria-00104481
@inproceedings{bhattacharya:inria-00104481,
    hal_id = {inria-00104481},
    url = {http://hal.inria.fr/inria-00104481},
    title = {{Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition}},
    author = {Bhattacharya, U. and Parui, S.K. and Shaw, B. and Bhattacharya, K.},
    abstract = {{In this article, a two-stage classification system for recognition of handwritten Devanagari numerals is presented. A shape feature vector computed from certain directional-view-based strokes of an input character image, has been used by both the HMM and ANN classifiers of the present recognition system. The two sets of posterior probabilities obtained from the outputs of the above two classifiers are combined by using another ANN classifier. Finally, the numeral image is classified according to the maximum score provided by the ANN of the second stage. In the proposed scheme, we achieved 92.83\% recognition accuracy on the test set of a recently developed large image database[1] of handwritten isolated numerals of Devanagari, the first and third most popular language and script in India and the world respectively. This recognition result improves the previously reported[2] accuracy of 91.28\% on the same data set.}},
    keywords = {Handwritten character recognition, Devanagari numeral recognition, HMM, ANN, Combination of classifiers},
    language = {English},
    affiliation = {Computer Vision and Pattern Recognition Unit - CVPR , Department of Computer Science \& Engineering},
    booktitle = {{Tenth International Workshop on Frontiers in Handwriting Recognition}},
    publisher = {Suvisoft},
    address = {La Baule (France)},
    organization = {Universit{\'e} de Rennes 1},
    editor = {Guy Lorette },
    note = {http://www.suvisoft.com Universit{\'e} de Rennes 1 },
    audience = {not specified },
    year = {2006},
    month = Oct,
    pdf = {http://hal.inria.fr/inria-00104481/PDF/cr1087131586696.pdf},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00104481"><analytic>
<author><persName><forename>U.</forename><surname>Bhattacharya</surname></persName>
<affiliation>
<orgName type="laboratory">CVPR</orgName>
<orgName type="team">Computer Vision and Pattern Recognition Unit</orgName>
<country>IN</country>
<orgName type="institution">Indian Statistical Institute</orgName>
</affiliation>
</author>
<author><persName><forename>S.K.</forename><surname>Parui</surname></persName>
<affiliation>
<orgName type="laboratory">CVPR</orgName>
<orgName type="team">Computer Vision and Pattern Recognition Unit</orgName>
<country>IN</country>
<orgName type="institution">Indian Statistical Institute</orgName>
</affiliation>
</author>
<author><persName><forename>B.</forename><surname>Shaw</surname></persName>
<affiliation>
<orgName type="laboratory">CVPR</orgName>
<orgName type="team">Computer Vision and Pattern Recognition Unit</orgName>
<country>IN</country>
<orgName type="institution">Indian Statistical Institute</orgName>
</affiliation>
</author>
<author><persName><forename>K.</forename><surname>Bhattacharya</surname></persName>
<affiliation>
<orgName type="team">Department of Computer Science & Engineering</orgName>
<country>IN</country>
<orgName type="institution">University of Calcutta</orgName>
</affiliation>
</author>
<title type="main" level="a">Neural Combination of ANN and HMM for Handwritten Devanagari Numeral Recognition</title></analytic><monogr><meeting>Tenth International Workshop on Frontiers in Handwriting Recognition</meeting><imprint><publisher>Suvisoft</publisher><pubPlace><settlement>La Baule (France)</settlement></pubPlace><biblScope type="publicationDate">2006-10-23</biblScope></imprint></monogr><idno type="HALid">http://hal.inria.fr/inria-00104481</idno><idno type="HALFile">http://hal.inria.fr/inria-00104481/PDF/cr1087131586696.pdf</idno></biblStruct>
</listBibl>
</listBibl>